[5/N][Attention] Finish eliminating vllm/attention folder (#32064)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
@@ -10,7 +10,6 @@ import torch
|
||||
import torch.nn as nn
|
||||
from transformers import MptConfig
|
||||
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
@@ -19,6 +18,7 @@ from vllm.distributed import (
|
||||
get_tensor_model_parallel_world_size,
|
||||
)
|
||||
from vllm.model_executor.layers.activation import get_act_fn
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.linear import (
|
||||
ColumnParallelLinear,
|
||||
QKVParallelLinear,
|
||||
|
||||
Reference in New Issue
Block a user